EuroEval Danish NLU - ScaLA DA: leaderboard
Metric: Linguistic acceptability Score (%). Source: euroeval.com. 432 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 77.98 |
| 2 | Gemini 3.1 Flash Lite (Preview) | 77.63 |
| 3 | Claude 3.7 Sonnet (20250219) (Thinking) | 76.38 |
| 4 | GPT-5 (High) | 75.53 |
| 5 | O3 (2025-04-16) | 74.15 |
| 6 | GPT-5 | 71.73 |
| 7 | GPT-5.2 | 71.48 |
| 8 | GPT-5.4 Mini (High) | 71.31 |
| 9 | Llama 3.1 405B | 70.64 |
| 10 | Claude Sonnet 4.6 | 70.3 |
| 11 | Gemini 2.5 Pro | 69.03 |
| 12 | Gemma 4 31B (IT) | 68.9 |
| 13 | Gemini 2.5 Pro (Preview 03-25) | 68.32 |
| 14 | GPT-5.4 Mini (Medium) | 68.28 |
| 15 | Claude Sonnet 4.5 (Thinking) | 67.78 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-danish-nlu-scala-da · How It Works · Data refreshed daily, snapshot 2026-09-05.